Fast sound source tracking method using two successive algorithms

In this paper, we propose a novel method for tracking two speakers using a microphone array based on successive algorithms: the PAST and IPLS algorithm. In a situation for which many sound sources exist simultaneously, the order of eigenvectors estimated by the PAST might be replaced in different time-frequency domains. It prevents separation and localization of each source. In addition, the appropriate initial values for the IPLS algorithm must be set after the silent intervals. For such difficulties, we propose a new method to put the eigenvectors in an appropriate order and a method to set a suitable initial value of the IPLS. Several experimental results in actual room environments are described to demonstrate the effectiveness of the proposed method.